K2 - mGEV: Extension of the GEV Activation to Multiclass Classification
Joshua Thomas Bridge, Yalin Zheng
Unbalanced data poses a challenge when training machine learning algorithms; the algorithm often overfits on the dominant class and neglects the smaller classes. While methods such as oversampling aim to rebalance the data, this can lead to overfitting. When a certain class is underrepresented, either because it a rare disease or few images exist then methods are needed which can adequately account for this. The generalized extreme value (GEV) activation has recently been proposed as a solution to highly unbalanced data; however, the GEV activation is only available for binary classification. We extend this to the multiclass case with the multiclass GEV (mGEV) activation. We conduct experiments on X-ray images, with three classes, showing much-improved performance over the commonly used softmax activation. Code for the mGEV activation is available at [https://github.com/JTBridge/GEV].
Friday 9th July
K1-9 (short): Learning with Noisy Labels and Limited Data - 16:45 - 17:30 (UTC+2)